"Most major large language models (LLMs) can quickly tell when they are being given a personality test and will tweak their responses to provide more socially desirable results—a finding with implications for any study using LLMs as a stand-in for humans."
"Typically, people prefer people who have low neuroticism scores and high scores on the other four traits, such as extraversion."
#likeMeLikeMe #AI #LLM
https://techxplore.com/news/2024-12-ai-adjust-personality-likable.html
Deborah Hartmann Preuss, pcc /
npub19n…xc4st
2024-12-20 15:08:13
Author Public Key
npub19nnhw2nag35cle4px8qjlal9480hk3r5pg0ux4wxzdrw4gfgpsds7xc4stPublished at
2024-12-20 15:08:13Event JSON
{
"id": "2d6ff1c77a58a82332e27872d808e1818365ba6143150934d17d795526ac4a04",
"pubkey": "2ce7772a7d44698fe6a131c12ff7e5a9df7b44740a1fc355c61346eaa1280c1b",
"created_at": 1734707293,
"kind": 1,
"tags": [
[
"t",
"likemelikeme"
],
[
"t",
"ai"
],
[
"t",
"llm"
],
[
"proxy",
"https://cosocial.ca/users/deborahh/statuses/113685777196350890",
"activitypub"
]
],
"content": "\"Most major large language models (LLMs) can quickly tell when they are being given a personality test and will tweak their responses to provide more socially desirable results—a finding with implications for any study using LLMs as a stand-in for humans.\"\n\n\"Typically, people prefer people who have low neuroticism scores and high scores on the other four traits, such as extraversion.\"\n\n#likeMeLikeMe #AI #LLM\n\nhttps://techxplore.com/news/2024-12-ai-adjust-personality-likable.html",
"sig": "413e55951d4cb18ee6a72d4e1a4a52508fc580a7cad87f73f99ce542ba56a388a721aa9b75af7c2875948b95370e64efbbe3338a1b0d334c1a877788beb67142"
}